k-Best hidden Markov model decoding for unit selection in concatenative sound synthesis
k-Best hidden Markov model decoding for unit selection in concatenative sound synthesis
Citació
- Nuanáin CÓ, Jordà S, Herrera P. k-Best hidden Markov model decoding for unit selection in concatenative sound synthesis. In: Aramaki M, Davies M, Kronland-Martinet R, Ystad S, editors. Music technology with swing. 13th International Symposium on Computer Music Multidisciplinary Research CMMR 2017; 2017 Sept 25-28; Matosinhos, Portugal. Springer: Cham; 2018. p. 76-97. (LNCS; no. 11265). DOI: 10.1007/978-3-030-01692-0_6
Enllaç permanent
Descripció
Resum
Concatenative synthesis is a sample-based approach to sound creation used frequently in speech synthesis and, increasingly, in musical contexts. Unit selection, a key component, is the process by which sounds are chosen from the corpus of samples. With their ability to match target units as well as preserve continuity, Hidden Markov Models are often chosen for this task, but one common criticism is its singular path output which is considered too restrictive when variations are desired. In this article, we propose considering the problem in terms of k-Best path solving for generating alternative lists of candidate solutions and summarise our implementations along with some practical examples.Descripció
Comunicació presentada a: The 13th International Symposium on Computer Music Multidisciplinary Research CMMR 201, celebrat del 25 al 28 de setembre de 2017 a Matosinhos, Portugal.